Learning Functionally Decomposed Hierarchies for Continuous Control Tasks with Path Planning


Date

2020-12-11

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

We present HiDe, a novel hierarchical reinforcement learning architecture that successfully solves long horizon control tasks and generalizes to unseen test scenarios. Functional decomposition between planning and low-level control is achieved by explicitly separating the state-action spaces across the hierarchy, which allows the integration of task-relevant knowledge per layer. We propose an RL-based planner to efficiently leverage the information in the planning layer of the hierarchy, while the control layer learns a goal-conditioned control policy. The hierarchy is trained jointly but allows for the composition of different policies such as transferring layers across multiple agents. We experimentally show that our method generalizes across unseen test environments and can scale to tasks well beyond 3x horizon length compared to both learning and non-learning based approaches. We evaluate on complex continuous control tasks with sparse rewards, including navigation and robot manipulation.

Publication status

published

External links

Editor

Book title

Journal / series

Volume

Pages / Article No.

Publisher

Deep RL Workshop

Event

Workshop: Deep Reinforcement Learning @NeurIPS 2020 (virtual)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Hierarchical reinforcement learning; Robotics; Path planning; Reinforcement Learning

Organisational unit

03979 - Hilliges, Otmar (ehemalig) / Hilliges, Otmar (former) check_circle

Notes

Due to the Coronavirus (COVID-19) the conference was conducted virtually.

Funding

717054 - Optimization-based End-User Design of Interactive Technologies (EC)

Related publications and datasets